Cover Image

Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Kaishuai, Yu, Tiezheng, Hou, Wenjun, Cheng, Yi, Leong, Chak Tou, Li, Liangyou, Jiang, Xin, Shang, Lifeng, Liu, Qun, Li, Wenjie
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework
by: Xu, Kaishuai, et al.
Published: (2025)

RAR$^2$: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval
by: Xu, Kaishuai, et al.
Published: (2025)

E2CL: Exploration-based Error Correction Learning for Embodied Agents
by: Wang, Hanlin, et al.
Published: (2024)

No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks
by: Leong, Chak Tou, et al.
Published: (2024)

AutoPal: Autonomous Adaptation to Users for Personal AI Companionship
by: Cheng, Yi, et al.
Published: (2024)

Reasoning Like a Doctor: Improving Medical Dialogue Systems via Diagnostic Reasoning Process Alignment
by: Xu, Kaishuai, et al.
Published: (2024)

Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry
by: Hou, Wenjun, et al.
Published: (2024)

Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis
by: Xu, Kaishuai, et al.
Published: (2024)

Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents
by: Wang, Hanlin, et al.
Published: (2026)

ICON: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentation
by: Hou, Wenjun, et al.
Published: (2024)

Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
by: Wang, Jian, et al.
Published: (2025)

Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
by: Xia, Heming, et al.
Published: (2025)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
by: Xia, Heming, et al.
Published: (2025)

STeCa: Step-level Trajectory Calibration for LLM Agent Learning
by: Wang, Hanlin, et al.
Published: (2025)

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
by: Leong, Chak Tou, et al.
Published: (2025)

Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
by: Leong, Chak Tou, et al.
Published: (2026)

SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution
by: Wang, Hanlin, et al.
Published: (2025)

RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injection
by: Hou, Wenjun, et al.
Published: (2025)

KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization
by: Song, Mingbo, et al.
Published: (2025)

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning
by: Yu, Erxin, et al.
Published: (2025)

Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback
by: Wang, Jiashuo, et al.
Published: (2024)

ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation
by: Zeng, Xingshan, et al.
Published: (2026)

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning
by: Wang, Zezhong, et al.
Published: (2025)

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
by: Jiang, Yuxin, et al.
Published: (2024)

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References
by: Zhang, Qiyuan, et al.
Published: (2024)

Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue
by: Wang, Jian, et al.
Published: (2024)

ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
by: Zeng, Xingshan, et al.
Published: (2025)

FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
by: Jiang, Yuxin, et al.
Published: (2023)

MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
by: Kwan, Wai-Chung, et al.
Published: (2024)

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis
by: Wang, Zezhong, et al.
Published: (2024)

Integrative Decoding: Improve Factuality via Implicit Self-consistency
by: Cheng, Yi, et al.
Published: (2024)

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
by: Yin, Qingyu, et al.
Published: (2025)

Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge
by: Zhang, Qiyuan, et al.
Published: (2025)

Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
by: Wang, Zezhong, et al.
Published: (2024)

Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models
by: Wang, Shuxun, et al.
Published: (2025)

ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning
by: Zeng, Xingshan, et al.
Published: (2025)

M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models
by: Kwan, Wai-Chung, et al.
Published: (2023)

Learning to Edit: Aligning LLMs with Knowledge Editing
by: Jiang, Yuxin, et al.
Published: (2024)

Protein as a Second Language for LLMs
by: Chen, Xinhui, et al.
Published: (2025)

Retrieval-based Disentangled Representation Learning with Natural Language Supervision
by: Zhou, Jiawei, et al.
Published: (2022)